Triple

T1709316
Position Surface form Disambiguated ID Type / Status
Subject Korean Empire E36940 entity
Predicate eraName P2938 FINISHED
Object Gwangmu E193590 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Gwangmu | Statement: [Korean Empire, eraName, Gwangmu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gwangmu
Context triple: [Korean Empire, eraName, Gwangmu]
  • A. Sunjong of Korea
    Sunjong of Korea was the final monarch of the Korean Empire, whose short and largely symbolic reign ended with Japan’s formal annexation of Korea in 1910.
  • B. Daehan Minguk
    Daehan Minguk is the Korean name for the Republic of Korea, the East Asian nation commonly known as South Korea.
  • C. Gojong of Korea chosen
    Gojong of Korea was the monarch who transformed the Joseon Kingdom into the Korean Empire and became its first emperor during a period of intense foreign pressure and modernization.
  • D. Joseongeul
    Joseongeul is the native Korean alphabetic writing system, more commonly known today as Hangul.
  • E. Sejong the Great
    Sejong the Great was a revered 15th-century Korean king of the Joseon Dynasty, best known for his sweeping cultural and scientific reforms that laid the foundations of Korea’s written and intellectual tradition.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69a88617439c819094ffb5d16a0f6307 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa631329088190a2ce8f755bd69fc7 completed March 6, 2026, 5:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69adbf46f51c8190bae3e47c97054188 completed March 8, 2026, 6:26 p.m.
Created at: March 4, 2026, 7:30 p.m.